Premium
Methods and Tools for Bayesian Variable Selection and Model Averaging in Normal Linear Regression
Author(s) -
Forte Anabel,
GarciaDonato Gonzalo,
Steel Mark
Publication year - 2018
Publication title -
international statistical review
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.051
H-Index - 54
eISSN - 1751-5823
pISSN - 0306-7734
DOI - 10.1111/insr.12249
Subject(s) - computer science , flexibility (engineering) , bayesian probability , bayesian linear regression , context (archaeology) , selection (genetic algorithm) , variable (mathematics) , linear regression , model selection , regression analysis , feature selection , regression , econometrics , machine learning , bayesian inference , data mining , artificial intelligence , statistics , mathematics , paleontology , biology , mathematical analysis
Summary In this paper, we briefly review the main methodological aspects concerned with the application of the Bayesian approach to model choice and model averaging in the context of variable selection in regression models. This includes prior elicitation, summaries of the posterior distribution and computational strategies. We then examine and compare various publicly available R ‐packages, summarizing and explaining the differences between packages and giving recommendations for applied users. We find that all packages reviewed (can) lead to very similar results, but there are potentially important differences in flexibility and efficiency of the packages.